摘要:
A depth estimation apparatus is provided. The depth estimation apparatus may estimate a depth value of at least one pixel composing an input video based on feature information about at least one feature of the input video, a position of the at least one pixel, and a depth relationship among the at least one pixel and neighboring pixels.
摘要:
A three-dimensional (3D) image generation apparatus and method using a region extension of an object in a depth map is provided. The 3D image generation apparatus may include a discontinuity preservation smoothing filtering unit to apply a discontinuity preservation smoothing filter preserving discontinuity of a boundary or a shape of a depth image, a boundary preservation filtering unit to apply a max filter to a depth image for increasing a depth value of an object, and a rendering unit to render a two-dimensional (2D) color image and the filtered depth image and to generate a 3D image.
摘要:
A three-dimensional (3D) image generation apparatus and method using a region extension of an object in a depth map is provided. The 3D image generation apparatus may include a discontinuity preservation smoothing filtering unit to apply a discontinuity preservation smoothing filter preserving discontinuity of a boundary or a shape of a depth image, a boundary preservation filtering unit to apply a max filter to a depth image for increasing a depth value of an object, and a rendering unit to render a two-dimensional (2D) color image and the filtered depth image and to generate a 3D image.
摘要:
A local multi-view image display apparatus and method is provided. The local multi-view image display method may track a location of an observer, and locally display a multi-view input image on the tracked location.
摘要:
A local multi-view image display apparatus and method is provided. The local multi-view image display method may track a location of an observer, and locally display a multi-view input image on the tracked location.
摘要:
A video processing method for a three-dimensional (3D) display is based on a multi-cue process. The method may include acquiring a cut boundary of a shot by performing a shot boundary detection with respect to each frame of an input video, computing a texture saliency with respect to each pixel of the input video, computing a motion saliency with respect to each pixel of the input video, computing an object saliency with respect to each pixel of the input video based on the acquired cut boundary of the shot, acquiring a universal saliency with respect to each pixel of the input video by combining the texture saliency, the motion saliency, and the object saliency, and smoothening the universal saliency of each pixel using a space-time technology.
摘要:
A method, apparatus, and medium of generating a visual attention map. A visual attention map to extract visual attention may be generated to convert a two-dimensional (2D) image into a three-dimensional (3D) image based on visual attention. The 2D image may be downscaled and at least one downscaled image may be generated. A feature map may be extracted from the 2D image and the at least one downscaled image, and the visual attention map may be generated.
摘要:
A video processing method for a three-dimensional (3D) display is based on a multi-cue process. The method may include acquiring a cut boundary of a shot by performing a shot boundary detection with respect to each frame of an input video, computing a texture saliency with respect to each pixel of the input video, computing a motion saliency with respect to each pixel of the input video, computing an object saliency with respect to each pixel of the input video based on the acquired cut boundary of the shot, acquiring a universal saliency with respect to each pixel of the input video by combining the texture saliency, the motion saliency, and the object saliency, and smoothening the universal saliency of each pixel using a space-time technology.
摘要:
Disclosed are an apparatus, a method and a computer-readable medium automatically generating a depth map corresponding to each two-dimensional (2D) image in a video. The apparatus includes an image acquiring unit to acquire a plurality of 2D images that are temporally consecutive in an input video, a saliency map generator to generate at least one saliency map corresponding to a current 2D image among the plurality of 2D images based on a Human Visual Perception (HVP) model, a saliency-based depth map generator, a three-dimensional (3D) structure matching unit to calculate matching scores between the current 2D image and a plurality of 3D typical structures that are stored in advance, and to determine a 3D typical structure having a highest matching score among the plurality of 3D typical structures to be a 3D structure of the current 2D image, a matching-based depth map generator; a combined depth map generator to combine the saliency-based depth map and the matching-based depth map and to generate a combined depth map, and a spatial and temporal smoothing unit to spatially and temporally smooth the combined depth map.
摘要:
A method, apparatus, and medium of generating a visual attention map. A visual attention map to extract visual attention may be generated to convert a two-dimensional (2D) image into a three-dimensional (3D) image based on visual attention. The 2D image may be downscaled and at least one downscaled image may be generated. A feature map may be extracted from the 2D image and the at least one downscaled image, and the visual attention map may be generated.